Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    sentence endings

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     spain
    0.48
     meestal
    0.47
     например
    0.46
    recated
    0.46
    zicht
    0.45
     idk
    0.45
    resión
    0.45
    ?,?,
    0.45
     %),
    0.45
    rowser
    0.44
    POSITIVE LOGITS
    .”
    0.56
    .’
    0.56
     एवं
    0.54
    ."
    0.51
    ፤
    0.51
    〝
    0.50
    께서
    0.50
    ፡፡
    0.49
     aforesaid
    0.49
     ಹಾಗೂ
    0.48
    Act Density 1.183%

    No Known Activations